AutoDeconJ: a GPU accelerated ImageJ plugin for 3D light field deconvolution with optimal iteration numbers predicting
Information Theory
2023-10-17 v1 math.IT
Abstract
Light field microscopy is a compact solution to high-speed 3D fluorescence imaging. Usually, we need to do 3D deconvolution to the captured raw data. Although there are deep neural network methods that can accelerate the reconstruction process, the model is not universally applicable for all system parameters. Here, we develop AutoDeconJ, a GPU accelerated ImageJ plugin for 4.4x faster and accurate deconvolution of light field microscopy data. We further propose an image quality metric for the deconvolution process, aiding in automatically determining the optimal number of iterations with higher reconstruction accuracy and fewer artifacts
Keywords
Cite
@article{arxiv.2208.11422,
title = {AutoDeconJ: a GPU accelerated ImageJ plugin for 3D light field deconvolution with optimal iteration numbers predicting},
author = {C. Q. Su and Y. H Gao and Y Zhou and Y. Q Sun and C. G Yan and H. B Yin and B Xiong},
journal= {arXiv preprint arXiv:2208.11422},
year = {2023}
}